Detection of steering events using hidden Markov models with multivariate observations
(2016) In International Journal of Vehicle Systems Modelling and Testing 11(4). p.313-329- Abstract
In this article we propose a method to identify steering events, such as curves and manoeuvres for vehicles. We use a hidden Markov model with multidimensional observations, to estimate the number of events. Three signals, lateral acceleration, steering angle speed and vehicle speed, are used as observations. We demonstrate that hidden Markov models with a combination of continuous and discrete distributions for observations can be used to detect steering events. Further, the expected number of events is estimated using the transition matrix of hidden states. The results from both measured and simulated data show that the method works well and accurately estimates the number of steering events.
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/39538e66-2451-414b-92ac-7d68cecbbd69
- author
- Maghsood, Roza ; Johannesson, Pär LU and Wallin, Jonas LU
- organization
- publishing date
- 2016-01-01
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- Discrete distribution, EM algorithm, hidden Markov models, Hmms, Laplace distribution, steering events
- in
- International Journal of Vehicle Systems Modelling and Testing
- volume
- 11
- issue
- 4
- pages
- 17 pages
- publisher
- Inderscience Publishers
- external identifiers
-
- scopus:85047075133
- ISSN
- 1745-6436
- DOI
- 10.1504/IJVSMT.2016.083752
- language
- English
- LU publication?
- yes
- id
- 39538e66-2451-414b-92ac-7d68cecbbd69
- date added to LUP
- 2018-05-30 15:58:50
- date last changed
- 2022-03-02 06:29:53
@article{39538e66-2451-414b-92ac-7d68cecbbd69, abstract = {{<p>In this article we propose a method to identify steering events, such as curves and manoeuvres for vehicles. We use a hidden Markov model with multidimensional observations, to estimate the number of events. Three signals, lateral acceleration, steering angle speed and vehicle speed, are used as observations. We demonstrate that hidden Markov models with a combination of continuous and discrete distributions for observations can be used to detect steering events. Further, the expected number of events is estimated using the transition matrix of hidden states. The results from both measured and simulated data show that the method works well and accurately estimates the number of steering events.</p>}}, author = {{Maghsood, Roza and Johannesson, Pär and Wallin, Jonas}}, issn = {{1745-6436}}, keywords = {{Discrete distribution; EM algorithm; hidden Markov models; Hmms; Laplace distribution; steering events}}, language = {{eng}}, month = {{01}}, number = {{4}}, pages = {{313--329}}, publisher = {{Inderscience Publishers}}, series = {{International Journal of Vehicle Systems Modelling and Testing}}, title = {{Detection of steering events using hidden Markov models with multivariate observations}}, url = {{http://dx.doi.org/10.1504/IJVSMT.2016.083752}}, doi = {{10.1504/IJVSMT.2016.083752}}, volume = {{11}}, year = {{2016}}, }